Hi,
I have been trying to run the Water-NSquared benchmark of the
Splash2-suite in Alpha FS Mode, but am encountering an unusual error.
First off, I have tried simulating working set sizes of 343, 512, and
1024.
I am able to correctly simulate the benchmark working set size of 512
for 4 and 8 core simulations, but am unable to simulate a 16 core
simulation for the smaller 343 working set size.
My understanding is that the number of cores being simulated should
not affect the simulated memory usage, but rather the benchmark itself
and input working set size.
I thought maybe there isn't enough swap space on the disk image (b/c
it returns 0), but that shouldn't be the case since it is just a
simulated machine. On closer inspection, it seems that the simulated
system is running out of memory.
I tried increasing the mem.size from the default 128MB to 1024MB in
/configs/common/Benchmark.py to no effect.
I am using the prebuilt parsec-disk image from UT-Austin. My host
machine has 12 GB, so increasing the mem.size to something as large as
1024 should be fine.
Has anyone else encountered a similar/same issue or have any suggestions?
The error is listed at the bottom:
Thanks in advance.
Malek
musleh@sherpa13:~/gem5_push3/util/term$ ./m5term localhost 3456
==== m5 slave terminal: Terminal 0 ====
Using 16 procs on 3 steps of 343 mols
Other parameters:
TSTEP = 1.50e-16
NORDER = 6
NSAVE = -1
NRST = 3000
NPRINT = 3
NFMC = 0
CUTOFF = 6.212752
WATER-NSQUARED invoked oom-killer: gfp_mask=0x1280d2, order=0, oomkilladj=0
fffffc000760bbe0 fffffc0000744b9a fffffc000037b798 0000000000000000
fffffc0000378de0 fffffc0000744b9a fffffc00003790f4 fffffc0007386280
00000000000001c1 fffffc000083c108 fffffc0007386280 0000000000000100
fffffc000083c108 fffffc0000744b9a fffffc000037b7c0 0000000000000000
fffffc0007386280 0000000000000000 0000000000000042 00000000001280d2
fffffc0000839f80 0000000000000000 0000000000000000 0000000000000003
Trace:
[<fffffc000037b798>] __alloc_pages_internal+0x4f8/0x580
[<fffffc0000378de0>] badness+0x170/0x250
[<fffffc00003790f4>] out_of_memory+0x234/0x2a0
[<fffffc000037b7c0>] __alloc_pages_internal+0x520/0x580
[<fffffc000038c1b4>] handle_mm_fault+0x494/0x820
[<fffffc000032af24>] do_page_fault+0x2d4/0x490
[<fffffc0000310a6c>] entMM+0x9c/0xc0
[<fffffc0000390624>] sys_brk+0xc4/0x180
[<fffffc0000390640>] sys_brk+0xe0/0x180
[<fffffc0000315920>] osf_brk+0x20/0x60
Mem-Info:
DMA per-cpu:
CPU 0: hi: 18, btch: 3 usd: 16
CPU 1: hi: 18, btch: 3 usd: 1
CPU 2: hi: 18, btch: 3 usd: 16
CPU 3: hi: 18, btch: 3 usd: 6
CPU 4: hi: 18, btch: 3 usd: 3
CPU 5: hi: 18, btch: 3 usd: 3
CPU 6: hi: 18, btch: 3 usd: 2
CPU 7: hi: 18, btch: 3 usd: 3
CPU 8: hi: 18, btch: 3 usd: 15
CPU 9: hi: 18, btch: 3 usd: 3
CPU 10: hi: 18, btch: 3 usd: 0
CPU 11: hi: 18, btch: 3 usd: 0
CPU 12: hi: 18, btch: 3 usd: 0
CPU 13: hi: 18, btch: 3 usd: 0
CPU 14: hi: 18, btch: 3 usd: 0
CPU 15: hi: 18, btch: 3 usd: 0
Active:13613 inactive:19 dirty:0 writeback:0 unstable:0
free:178 slab:798 mapped:0 pagetables:32 bounce:0
DMA free:1424kB min:1440kB low:1800kB high:2160kB active:108904kB
inactive:152kB present:130176kB pages_scanned:85027 all_unreclaimable?
yes
lowmem_reserve[]: 0 0 0
DMA: 1*8kB 1*16kB 1*32kB 1*64kB 0*128kB 0*256kB 0*512kB 1*1024kB
0*2048kB 0*4096kB 0*8192kB = 1144kB
16 total pagecache pages
0 pages in swap cache
Swap cache stats: add 0, delete 0, find 0/0
Free swap = 0kB
Total swap = 0kB
16384 pages RAM
1282 pages reserved
47 pages shared
14663 pages non-shared
Out of memory: kill process 879 (WATER-NSQUARED) score 859 or a child
Killed process 879 (WATER-NSQUARED)
_______________________________________________
gem5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
